{"id":3103124,"url":"https://alion.io/job/stanbridge-university-software-engineer-ai-systems-go","title":"Software Engineer - AI Systems (Go)","company":{"id":685911,"name":"Stanbridge University","domain":"stanbridge.edu","url":"https://alion.io/company/stanbridge-2","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Workable","truth_index":null},"role":"Backend","role_family":"Backend","seniority":null,"employment_type":"full_time","work_mode":"remote","remote_scope":"stated_countries","remote_scope_basis":"posting_text","remote_working_hours":null,"hiring_geo_confidence":"explicit","locations":["Irvine, United States"],"countries":["US"],"hiring_countries":["US"],"hiring_countries_total":1,"salary":null,"salary_estimate":{"min_usd":97000,"max_usd":209000,"period":"year","method":"role_country_seniority_unknown","sample_n":9411},"experience_years_min":null,"visa_sponsorship":true,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"Go","optional":false},{"name":"Human-in-the-Loop","optional":false},{"name":"LLM","optional":false},{"name":"LLM Evaluation","optional":false},{"name":"Prompt Engineering","optional":false},{"name":"SQL","optional":false},{"name":"CI/CD","optional":true},{"name":"Embeddings","optional":true},{"name":"RAG","optional":true},{"name":"Semantic Search","optional":true},{"name":"Text-to-Speech","optional":true}],"status":"closed","first_seen_at":"2026-10-22T18:03:00Z","employer_posted_date":"2026-10-22","last_verified_at":"2026-10-27T19:37:49Z","board_verified":false,"closed_at":"2026-10-27T19:37:49Z","days_open":5,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":5},"description":"Stanbridge University is seeking Software Engineers - AI Systems (Go) to design, build, and operate production AI systems that perform complex, multi-stage work reliably and at scale.\nThis is a hands-on engineering role focused on a challenging class of problems: long-running AI workflows that call models, tools, and external APIs; maintain state across extended executions; produce structured content and generated media; interact with human reviewers; recover from partial failures; and consistently deliver accurate results to users.\nThe core engineering challenges extend well beyond prompt development. These systems must account for provider failures and rate limits, interrupted workflows, changing state, non-deterministic model behavior, incorrect or unsupported outputs, variable latency and cost, and deployments occurring while work is in progress.\nThe successful candidate will combine strong software and distributed-systems engineering judgment with practical experience building and operating LLM-backed applications, AI agents, or agent-based systems in production.\nYou will join at a stage where significant architecture remains to be designed and built. Engineers in this role will have substantial ownership over the patterns, services, infrastructure, and engineering standards that shape the University's AI systems.\nRemote Work Eligibility\nThis position is eligible for remote work for candidates residing in states where Stanbridge University is currently authorized to employ remote employees. Eligible states currently include: Arizona, Colorado, Illinois, Indiana, Kansas, Kentucky, Louisiana, Maryland, Michigan, Minnesota, Nevada, New Jersey, North Carolina, North Dakota, Ohio, Tennessee, Texas, and Wisconsin.\nCandidates must reside in an eligible state at the time of employment. Remote-work eligibility is subject to University employment requirements and may change based on applicable state requirements.\nEngineering Environment\nThe engineering problems addressed by this team include:\nDurable workflow orchestration: Long-running, multi-stage pipelines using persistent state, job queues, checkpoints, resumability, idempotent execution, and recovery from interrupted or orphaned work.\nMulti-provider model infrastructure: Routing across commercial model providers with model registries, token and cost controls, rate-limit handling, retries, circuit breakers, health monitoring, and provider failover.\nAgent and tool orchestration: Systems in which AI agents interact with tools, APIs, data sources, application services, and deterministic business logic to complete multi-step work.\nPrompt engineering infrastructure: Treating prompts as version-controlled production artifacts with review, testing, regression protection, and measurable behavior.\nTesting non-deterministic systems: Recorded and replayable provider interactions, deterministic fixtures, evaluation harnesses, baselines, and regression testing for AI behavior.\nCorrectness and quality controls: Structured-output validation, automated evaluation, domain-specific requirements, evidence checking, and safeguards against confident but incorrect model output.\nHuman-in-the-loop workflows: Review and approval stages within automated processes, including systems capable of safely responding when users modify state or inputs during execution.\nGenerated media pipelines: Systems capable of producing and managing documents, audio, imagery, video, and other generated assets.\nProduction service architecture: Go-based APIs and backend services, relational data stores, job infrastructure, observability, and integrations supporting user-facing applications.\nSecure ingestion: Processing user-supplied and potentially untrusted documents while maintaining appropriate security and authorization boundaries.\nTwo Engineering Emphases\nEngineers will meet the same overall technical bar but may bring deeper expertise in one of two areas:\nPlatform and Pipeline\nFocused on distributed systems, workflow orchestration, durable state, job queues, recovery, provider infrastructure, latency, throughput, scalability, reliability, and cost optimization.\nThis emphasis is particularly well suited for experienced systems engineers who view AI models as powerful components that introduce a new set of distributed-systems and reliability challenges.\nAgents and Quality\nFocused on agent and tool architecture, prompt systems, context management, evaluation frameworks, regression testing, judge models, evidence validation, and end-to-end output quality.\nThis emphasis is particularly well suited for engineers who approach AI behavior through experimentation, measurement, testing, and systematic improvement.\nCandidates may indicate an area of preference; however, specialization in one area is not required.\nEssential Functions\nDesign, develop, test, deploy, and operate production-quality software and backend services, primarily using Go (Golang).\nArchitect and build AI agents and agent-based systems capable of using tools, interacting with APIs, maintaining state and context, and executing complex multi-step workflows.\nDesign durable workflows that can checkpoint, resume, retry, recover, and safely continue execution following partial failures or system interruptions.\nDetermine how models, agents, tools, APIs, data sources, services, and deterministic application logic should divide responsibilities within an AI system, including recognizing when an AI model is not the appropriate solution.\nDesign integrations across multiple AI model providers, including routing, failover, rate-limit management, health monitoring, and degradation strategies.\nBuild safeguards including structured-output validation, error handling, retries, quality gates, evidence validation, and automated recovery mechanisms.\nDevelop testing strategies for non-deterministic AI behavior using techniques such as deterministic fixtures, recorded and replayed interactions, regression suites, evaluation harnesses, and quality baselines.\nDevelop observability capabilities including tracing, metrics, logging, evaluation data, and replayable execution histories to support production debugging and performance analysis.\nDesign human-in-the-loop workflows incorporating review, approval, intervention, and modification of workflow state.\nBuild and maintain APIs, backend services, relational data models, job-processing infrastructure, and supporting application components.\nDevelop secure methods for ingesting and processing user-supplied documents and other external content.\nOptimize systems for reliability, latency, throughput, scalability, output quality, and cost per execution.\nBuild reusable engineering patterns and shared components that simplify the addition of new agents, model providers, tools, workflows, and output types.\nOwn technical problems from initial investigation and architecture through implementation, deployment, monitoring, troubleshooting, and ongoing production operation.\nCollaborate directly with product stakeholders and domain experts to translate qualitative requirements into measurable system behavior and technical solutions.\nContribute to architectural decisions and engineering standards for AI-powered applications across the University.\nQualifications\nRequired\nSubstantial professional experience developing and operating production software, with strong experience in Go (Golang) or demonstrated depth in another backend language with the ability to become productive in Go quickly.\nHands-on experience shipping an LLM-backed application, AI agent, or agent-based system into production and supporting it after deployment.\nStrong understanding of AI application architecture, including how models, agents, tools, APIs, data sources, services, and application logic interact.\nDemonstrated distributed-systems engineering knowledge, including concurrency, asynchronous processing, queues, idempotency, retries, partial failure, state management, and recovery.\nExperience designing systems that remain reliable when individual services, providers, or workflow stages fail.\nDemonstrated testing discipline for systems involving non-deterministic behavior.\nStrong experience designing and consuming HTTP APIs.\nExperience with relational databases, SQL, and persistent application state.\nExperience building, deploying, monitoring, and troubleshooting backend services in production environments.\nUnderstanding of software architecture, testing, debugging, observability, and production engineering practices.\nAbility to independently own ambiguous technical problems from investigation through production implementation.\nStrong analytical judgment and the ability to balance reliability, quality, performance, complexity, and cost.\nPreferred Qualifications\nExperience with AI agent frameworks, orchestration patterns, or custom agent architectures, including an understanding of when a framework may not be appropriate.\nExperience with retrieval-augmented generation (RAG), embeddings, vector databases, semantic search, or knowledge-retrieval architectures.\nExperience developing evaluation and observability systems for LLM applications, including tracing, regression suites, quality dashboards, or automated evaluation.\nExperience with judge models, structured-output validation, evidence checking, or other AI quality-control mechanisms.\nExperience designing human-in-the-loop workflows involving review, approval, intervention, or modification of active workflow state.\nExperience with document processing, headless-browser rendering, text-to-speech, image generation, video generation, or other media pipelines.\nExperience with event-driven architectures, durable job queues, and asynchronous processing at scale.\nExperience with containers, cloud infrastructure, CI/CD, and production deployment environments.\nUnderstanding of prompt injection, authorization boundaries, data isolation, and security considerations when untrusted content is processed by AI systems.\nExperience developing systems in environments where the accuracy of generated output carries significant operational, regulatory, compliance, or safety implications.\nWhat Success Looks Like\nAn exceptional engineer in this role will:\nBuild AI workflows that operate reliably in production without requiring routine human intervention.\nDesign systems that recover gracefully from model-provider failures, interrupted execution, deployments, rate limits, and other partial failures.\nMake AI behavior increasingly measurable, reproducible, testable, and observable rather than relying on subjective evaluation.\nImprove output quality while systematically reducing latency and cost per execution.\nCreate durable engineering patterns that make subsequent agents, providers, workflows, and output types easier and safer to introduce.\nIdentify when deterministic software should replace or constrain model-driven behavior.\nBuild systems whose failures can be diagnosed through instrumentation and replay rather than guesswork.\nEstablish architecture and engineering practices that become foundational components of the University's broader AI capabilities.\nCompensation\nCompensation is based on education, experience, and qualifications and internal equity\nConditions of Employment:\n A job-related assessment may be required during the interview process.\n Must be able to perform each essential duty satisfactorily and be physically present in the office (unless otherwise noted).\n Employment Authorization: Applicants must be legally authorized to work in the United States. Stanbridge University does not provide employment-based immigration sponsorship or participate in employer-sponsored or employer-dependent work authorization programs.\n Sponsorship: Sponsorship now or in the future could include having Stanbridge University sponsor, complete employer documentation, provide attestations or training plans, or otherwise participate in a work-authorization or employment-based immigration program in order for a...","description_format":"text","description_chars":15051,"description_truncated":true,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"bachelor","optional":false},"security_clearance":false,"languages":[]},"benefits":["401k plan","Equity","Life insurance","Parental leave","Retirement plans"],"hiring_locations":[{"name":"United States","iso":"US","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Artificial Intelligence","Education","Higher Education"],"lifecycle":[{"event":"open","at":"2026-10-22T18:03:00Z"},{"event":"close","at":"2026-10-27T19:37:49Z"}],"visa":[],"liveness":null,"pay":null,"html_url":"https://alion.io/job/stanbridge-university-software-engineer-ai-systems-go","json_url":"https://alion.io/job/stanbridge-university-software-engineer-ai-systems-go.json","meta":{"generated_at":"2026-10-28T02:18:34Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":3100,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-29T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":685911},"rest":"https://alion.io/mcp/rest/get_company?id=685911"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fstanbridge-university-software-engineer-ai-systems-go"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Fstanbridge-university-software-engineer-ai-systems-go"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Fstanbridge-university-software-engineer-ai-systems-go"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/stanbridge-university-software-engineer-ai-systems-go\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fstanbridge-university-software-engineer-ai-systems-go"}]}